{"id":"https://openalex.org/W2107333973","doi":"https://doi.org/10.1145/1669112.1669119","title":"Complexity effective memory access scheduling for many-core accelerator architectures","display_name":"Complexity effective memory access scheduling for many-core accelerator architectures","publication_year":2009,"publication_date":"2009-12-12","ids":{"openalex":"https://openalex.org/W2107333973","doi":"https://doi.org/10.1145/1669112.1669119","mag":"2107333973"},"language":"en","primary_location":{"id":"doi:10.1145/1669112.1669119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1669112.1669119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004571219","display_name":"George L. Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"George L. Yuan","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","Dept of Electrical & Computer Engineering, University of British Columbia, Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Dept of Electrical & Computer Engineering, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037238310","display_name":"Ali Bakhoda","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ali Bakhoda","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","Dept of Electrical & Computer Engineering, University of British Columbia, Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Dept of Electrical & Computer Engineering, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026788167","display_name":"Tor M. Aamodt","orcid":"https://orcid.org/0000-0003-1161-692X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tor M. Aamodt","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","Dept of Electrical & Computer Engineering, University of British Columbia, Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Dept of Electrical & Computer Engineering, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004571219"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":6.1585,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.96821493,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7712522745132446},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5007352828979492},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4987611770629883},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.4284977614879608},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41527464985847473},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0862572193145752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712522745132446},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5007352828979492},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4987611770629883},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.4284977614879608},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41527464985847473},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0862572193145752},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1669112.1669119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1669112.1669119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.465.1289","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.465.1289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://137.82.61.1/~aamodt/papers/gyuan.micro2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W63944998","https://openalex.org/W1979527452","https://openalex.org/W2098040113","https://openalex.org/W2102871765","https://openalex.org/W2115172404","https://openalex.org/W2126169247","https://openalex.org/W2128022558","https://openalex.org/W2132292283","https://openalex.org/W2149897852","https://openalex.org/W2162838417","https://openalex.org/W2169150396","https://openalex.org/W2295787458","https://openalex.org/W2399306013","https://openalex.org/W4236382111","https://openalex.org/W4247913514","https://openalex.org/W6602613798"],"related_works":["https://openalex.org/W2117014006","https://openalex.org/W4233815414","https://openalex.org/W2372170743","https://openalex.org/W1558545464","https://openalex.org/W2074301136","https://openalex.org/W1984303163","https://openalex.org/W1509211761","https://openalex.org/W4297677116","https://openalex.org/W2793542907","https://openalex.org/W4308087753"],"abstract_inverted_index":{"Modern":[0],"DRAM":[1,23,79,97,104,127,151,178,206,254,303],"systems":[2],"rely":[3],"on":[4,45],"memory":[5,47,110,141,159,198,247,267,295],"controllers":[6],"that":[7,108,165,190,213,272],"employ":[8,184],"out-of-order":[9,53,103,217,294],"scheduling":[10,54,68,220],"to":[11,65,78,100,119,125,149,154,212,264,286],"maximize":[12,126],"row":[13,122,168,193],"access":[14,123,169,194],"lo-cality":[15],"and":[16,208,238,256],"bank-level":[17],"parallelism,":[18],"which":[19,82,140],"in":[20,29,58,129,162,202],"turn":[21],"maximizes":[22],"bandwidth.":[24],"This":[25],"is":[26],"especially":[27,62],"important":[28],"graphics":[30],"processing":[31],"unit":[32],"(GPU)":[33],"architectures,":[34],"where":[35],"the":[36,46,86,109,136,146,150,157,167,172,177,192,289],"large":[37],"quan-tity":[38],"of":[39,60,85,171,196,245,288],"parallelism":[40],"places":[41],"a":[42,75,91,163,225,242,279,298],"heavy":[43],"demand":[44],"system.":[48],"The":[49],"logic":[50],"needed":[51],"for":[52,241,297],"can":[55],"be":[56],"expensive":[57],"terms":[59],"area,":[61],"when":[63],"compared":[64,99],"an":[66,101,185,293],"in-order":[67,93,282],"approach.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,183],"propose":[74],"complexity-effective":[76],"solution":[77],"request":[80,111,160,199,219],"schedul-ing":[81],"recovers":[83],"most":[84,130],"performance":[87,290],"loss":[88],"incurred":[89],"by":[90,215,251],"naive":[92],"first-in":[94],"first-out":[95],"(FIFO)":[96],"scheduler":[98,283,296],"aggressive":[102],"scheduler.":[105],"We":[106,228],"observe":[107],"stream":[112,174],"from":[113,145],"individual":[114,197],"GPU\u201cshader":[115],"cores":[116,148,259],"\u201d":[117],"tends":[118,153],"have":[120],"sufficient":[121],"local-ity":[124],"efficiency":[128,207],"applications":[131],"with-out":[132],"significant":[133],"reordering.":[134],"However,":[135],"interconnection":[137,231],"net-work":[138],"across":[139],"requests":[142],"are":[143],"sent":[144],"shader":[147,258],"controller":[152,255,304],"finely":[155],"interleave":[156],"numerous":[158],"streams":[161,200],"way":[164],"destroys":[166],"locality":[170,195],"resultant":[173],"seen":[175],"at":[176],"controller.":[179],"To":[180],"address":[181],"this,":[182],"intercon-nection":[186],"network":[187,232,300],"arbitration":[188,233,275],"scheme":[189,234,276],"preserves":[191],"and,":[201],"doing":[203,222],"so,":[204],"achieves":[205],"system":[209],"perfor-mance":[210],"close":[211],"achievable":[214],"using":[216,235],"mem-ory":[218],"while":[221],"so":[223],"with":[224,278,292,301],"simpler":[226],"de-sign.":[227],"evaluate":[229],"our":[230,273],"crossbar,":[236],"mesh,":[237],"ring":[239],"networks":[240],"base-line":[243],"architecture":[244],"8":[246],"channels,":[248],"each":[249],"controlled":[250],"its":[252],"own":[253],"28":[257],"(224":[260],"ALUs),":[261],"supporting":[262],"up":[263,285],"1,792":[265],"in-flight":[266],"requests.":[268],"Our":[269],"re-sults":[270],"show":[271],"interconnect":[274],"coupled":[277],"banked":[280],"FIFO":[281],"obtains":[284],"91%":[287],"obtainable":[291],"crossbar":[299],"eight-entry":[302],"queues.":[305]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
